I seriously hate to post a question about an entire chunk of code, but I've been working on this for the past 3 hours and I can't wrap my head around what is happening. I have approximately 600 tweets I am retrieving from a CSV file with varying score values (between -2 to 2) reflecting the sentiment towards a presidential candidate.
However, when I run this training sample on any other data, only one value is returned (positive). I have checked to see if the scores were being added correctly and they are. It just doesn't make sense to me that 85,000 tweets would all be rated "positive" from a diverse training set of 600. Does anyone know what is happening here? Thanks!
import nltk
import csv
tweets = []
import ast
with open('romney.csv', 'rb') as csvfile:
mycsv = csv.reader(csvfile)
for row in mycsv:
tweet = row[1]
try:
score = ast.literal_eval(row[12])
if score > 0:
print score
print tweet
tweets.append((tweet,"positive"))
elif score < 0:
print score
print tweet
tweets.append((tweet,"negative"))
except ValueError:
tweet = ""
def get_words_in_tweets(tweets):
all_words = []
for (words, sentiment) in tweets:
all_words.extend(words)
return all_words
def get_word_features(wordlist):
wordlist = nltk.FreqDist(wordlist)
word_features = wordlist.keys()
return word_features
def extract_features(document):
document_words = set(document)
features = {}
for word in word_features:
features['contains(%s)' % word] = (word in document_words)
return features
word_features = get_word_features(get_words_in_tweets(tweets))
training_set = nltk.classify.apply_features(extract_features, tweets)
classifier = nltk.NaiveBayesClassifier.train(training_set)
c = 0
with open('usa.csv', "rU") as csvfile:
mycsv = csv.reader(csvfile)
for row in mycsv:
try:
tweet = row[0]
c = c + 1
print classifier.classify(extract_features(tweet.split()))
except IndexError:
tweet = ""